清华大佬耗费三个月吐血整理的几百G的资源，免费分享！....>>>

# -*- coding:utf-8 -*-
__author__ = 'Barry'


from PIL import Image
from PIL.ExifTags import TAGS
from datetime import datetime
from hashlib import md5
import time
import os
import shutil
import fnmatch
import random


def IterFindFiles(path, fnexp):
    for root, dirs, files in os.walk(path):
        for filename in fnmatch.filter(files, fnexp):
            yield os.path.join(root, filename)

def GenRandomStr():
    str = ''
    chars = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890'
    for num in range(10):
        str += random.choice(chars)
    return str

def GetPicPath():
    pic_full_path = []
    if os.path.isdir(input_path):
        for i in os.listdir(input_path):
            sub_dir = input_path + '/' + i
            if os.path.isdir(sub_dir):
                for n in os.listdir(sub_dir):
                    pic_full_path.append(sub_dir + '/' + n)
    return pic_full_path


def print_all_know_exif_tags():
	for k in sorted(TAGS):
		print k, TAGS[k]

def FormatTime(date):
    try:
        ts = time.mktime(time.strptime(date,'%Y:%m:%d %H:%M:%S'))
        return time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(ts))
    except Exception, e:
        return False

def TrimTime(mtime):
    ts = time.mktime(time.strptime(mtime,'%Y-%m-%d %H:%M:%S'))
    return time.strftime('%Y%m%d',time.localtime(ts))

def CalcDays(mtime,birth_day):
    time_fmt = '%Y%m%d'
    days_born = (datetime.strptime(mtime,time_fmt) - datetime.strptime(birth_day,time_fmt)).days
    return str(days_born + 1)

def GenMd5(filename):
    file_tmp = open(filename,'rb')
    md5_value = md5(file_tmp.read())
    file_tmp.close()
    return md5_value.hexdigest()

def GetPicExif():
    pic_date = {}
    #pic_path = GetPicPath()
    for filename in IterFindFiles(input_path,fnexp):
        mtime = time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(os.stat(filename).st_mtime))
    	try:
            img = Image.open(filename)
    	except Exception, e:
    		print filename,"skipping due to ",e
        try:
            exif_data = img._getexif()
        except Exception, e:
            print filename,"skipping due to ",e
        finally:
            if exif_data:
                if exif_data.has_key(36867):
                    pic_date[filename] = FormatTime(exif_data[36867]) and FormatTime(exif_data[36867])  or mtime
                elif exif_data.has_key(36868):
                    pic_date[filename] = FormatTime(exif_data[36868]) and FormatTime(exif_data[36868])  or mtime
                elif exif_data.has_key(306):
                    pic_date[filename] = FormatTime(exif_data[306]) and FormatTime(exif_data[306]) or mtime
                else:
                    pic_date[filename] = mtime
            else:
                pic_date[filename] = mtime

    return pic_date

def ArchivePic():
    pic_date = GetPicExif()
    new_dir_file_md5_list = []
    for pic,mtime in pic_date.items():
        std_out = "\033[1;33mAdd new picture \033[1;31m%s\033[0m\033[1;33m to dest path:%s\033[0m"%(os.path.split(pic)[1],output_path)
        new_dir = "%s/%s-(%sdays)"%(output_path,TrimTime(mtime),CalcDays(TrimTime(mtime),birth_day))
        if not os.path.exists(new_dir):
            os.mkdir(new_dir)
        new_file_name = '%s-%s-%s%s'%(pic_prefix,TrimTime(mtime),GenRandomStr(),pic_suffix)
        new_file_path = '%s/%s'%(new_dir,new_file_name)
        if not os.path.exists(new_file_path):
            try:
                if os.listdir(new_dir):
                    for i in os.listdir(new_dir):
                        hashvalue = GenMd5(os.path.join(new_dir,i))
                        new_dir_file_md5_list.append(hashvalue)
                    if GenMd5(pic) not in new_dir_file_md5_list:
                        shutil.copy2(pic,new_file_path)
                        print std_out
                else:
                    shutil.copy2(pic,new_file_path)
                    print std_out
            except Exception, e:
                print e
        else:
            while True:
                new_file_name = '%s-%s-%s%s'%(pic_prefix,TrimTime(mtime),GenRandomStr(),pic_suffix)
                if new_file_name not in os.lisdir(new_dir):
                    break
                else:
                    continue
            new_file_path = '%s/%s'%(new_dir,new_file_name)
            for i in os.listdir(new_dir):
                hashvalue = GenMd5(os.path.join(new_dir,i))
                new_dir_file_md5_list.append(hashvalue)
            if GenMd5(pic) not in new_dir_file_md5_list:
                try:
                    shutil.copy2(pic,new_file_path)
                    print std_out
                except Exception, e:
                    print e
    return 


if __name__ == "__main__":
    #input_path = r"D:\baby/"
    input_path = r"C:\users\xxr12\onedrive\pictures"
    #input_path = r"E:\MemArchPic"
    output_path = r"E:\Mybaby"
    fnexp = "*.jpg"
    pic_suffix = ".jpg"   #如果查找的是jpg文件，那文件后缀名也要匹配
    pic_prefix = "MYBABY"
    birth_day = '20150621'
    if not os.path.exists(output_path): 
        os.mkdir(output_path)
    if not os.path.exists(input_path):
        print "some of path not found!"
    else:
        ArchivePic()
    #print_all_know_exif_tags()